© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75277
    Prev
    Next
    INDEX
    Explanations

    market trends and systems

    np_acts-logits-general · gemini-2.5-flash-lite

    information about specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лія
    0.52
    Chicago
    0.49
    ла
    0.49
    лії
    0.49
    ا۔
    0.48
    Valencia
    0.48
    American
    0.46
    ا
    0.45
    Illinois
    0.44
    Alger
    0.44
    POSITIVE LOGITS
    jpg
    0.51
     gamers
    0.49
     streamer
    0.45
    springframework
    0.44
    numpy
    0.42
     hourglass
    0.42
     gaming
    0.41
    header
    0.40
     bootstra
    0.40
     backpack
    0.40
    Activations Density 0.000%

    No Known Activations